Zerank 2 vs Cohere Rerank 4 Pro

Detailed comparison between Zerank 2 and Cohere Rerank 4 Pro. See which reranker best meets your accuracy and performance needs. If you want to compare these models on your data, try Agentset.

Model Comparison

Cohere Rerank 4 Pro takes the lead.

Both Zerank 2 and Cohere Rerank 4 Pro are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Cohere Rerank 4 Pro:

  • Cohere Rerank 4 Pro delivers better accuracy (nDCG@10: 0.095 vs 0.079)

Overview

Key metrics

ELO Rating

Overall ranking quality

Zerank 2

1638

Cohere Rerank 4 Pro

1629

Win Rate

Head-to-head performance

Zerank 2

57.2%

Cohere Rerank 4 Pro

57.7%

Accuracy (nDCG@10)

Ranking quality metric

Zerank 2

0.079

Cohere Rerank 4 Pro

0.095

Average Latency

Response time

Zerank 2

265ms

Cohere Rerank 4 Pro

614ms

Rerankers Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no reranking to configure.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Visual Performance Analysis

Performance

ELO Rating Comparison

Win/Loss/Tie Breakdown

Accuracy Across Datasets (nDCG@10)

Latency Distribution (ms)

Breakdown

How the models stack up

MetricZerank 2Cohere Rerank 4 ProDescription
Overall Performance
ELO Rating
1638
1629
Overall ranking quality based on pairwise comparisons
Win Rate
57.2%
57.7%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.025
$0.050
Cost per million tokens processed
Release Date
2025-11-18
2025-12-11
Model release date
Accuracy Metrics
Avg nDCG@10
0.079
0.095
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
265ms
614ms
Average response time across all datasets

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked rerankers and embedding models built in. Upload your data, call the API, and get accurate results from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Dataset Performance

By field

Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.

MSMARCO

MetricZerank 2Cohere Rerank 4 ProDescription
Latency Metrics
Mean
233ms
458ms
Average response time
P50
228ms
408ms
50th percentile (median)
P90
251ms
615ms
90th percentile

arguana

MetricZerank 2Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.283
0.353
Ranking quality at top 5 results
nDCG@10
0.355
0.439
Ranking quality at top 10 results
Recall@5
0.540
0.660
% of relevant docs in top 5
Recall@10
0.760
0.920
% of relevant docs in top 10
Latency Metrics
Mean
280ms
785ms
Average response time
P50
278ms
768ms
50th percentile (median)
P90
312ms
933ms
90th percentile

FiQa

MetricZerank 2Cohere Rerank 4 ProDescription
Accuracy Metrics
nDCG@5
0.108
0.126
Ranking quality at top 5 results
nDCG@10
0.119
0.129
Ranking quality at top 10 results
Recall@5
0.098
0.130
% of relevant docs in top 5
Recall@10
0.130
0.135
% of relevant docs in top 10
Latency Metrics
Mean
251ms
610ms
Average response time
P50
254ms
585ms
50th percentile (median)
P90
270ms
817ms
90th percentile

business reports

MetricZerank 2Cohere Rerank 4 ProDescription
Latency Metrics
Mean
288ms
529ms
Average response time
P50
269ms
498ms
50th percentile (median)
P90
367ms
675ms
90th percentile

PG

MetricZerank 2Cohere Rerank 4 ProDescription
Latency Metrics
Mean
293ms
760ms
Average response time
P50
281ms
720ms
50th percentile (median)
P90
328ms
896ms
90th percentile

DBPedia

MetricZerank 2Cohere Rerank 4 ProDescription
Latency Metrics
Mean
247ms
541ms
Average response time
P50
242ms
489ms
50th percentile (median)
P90
274ms
729ms
90th percentile

Explore More

Compare more rerankers

See how all reranking models stack up. Compare Cohere, Jina AI, Voyage, ZeRank, and more. View comprehensive benchmarks, compare performance metrics, and find the perfect reranker for your RAG application.